AI Runtime Solutions Architect for Scalable Inference

CoreWeave; New York (NY); On-site; USD 207,000 - 275,000; Full time

Benefits offered by this job

Medical, dental, and vision insurance—

401(k) with generous match

Flexible PTO

Tuition Reimbursement

ESPP

Job summary

CoreWeave is seeking a Solution Specialist for AI Runtime Services to bring new runtime offerings to market and drive early adoption. You will own the commercial and technical strategy for net new customer wins, focusing on high-throughput model serving and secure multi-tenant execution.

You will shape roadmaps with product and engineering, engage enterprise buyers, and craft deal structures that accelerate adoption of Inference and Sandboxes, leveraging performance tradeoffs and cost-per-token

Qualifications

• 10+ years in distributed systems, ML infrastructure, or production AI engineering.
• 5+ years with AI runtime systems in a customer-facing or deal-shaping capacity.
• Deep knowledge of runtime execution, serving frameworks, batching, and throughput/latency at scale.
• Experience with sandboxed and isolated execution environments and multi-tenant scheduling.
• Strong understanding of GPU memory hierarchies and cost/latency tradeoffs.
• Familiarity with Kubernetes-native runtime orchestration and workload portability.
• Ability to benchmark, explain, and commercially position runtime performance differences.

Responsibilities

• Own the commercial and technical strategy for net new customer wins in AI runtime infrastructure.
• Drive opportunities where latency, throughput, or isolation are barriers to scaling AI on CoreWeave.
• Develop deep expertise across AI runtime landscape using Inference and Sandboxes as flagship examples.
• Translate customer requirements into product feedback shaping the AI Runtime Services roadmap.
• Develop deal structures, playbooks, and benchmark narratives for sales and SA teams.
• Engage directly with enterprise buyers as the voice on performance, cost-per-token, and architecture decisions.
• Design the commercial framework for large-scale runtime deployment deals, including throughput and SLA structures.
• Partner with product and infra teams to maintain a competitive edge on efficiency and reliability.

Skills

Distributed systems

ML infrastructure

Deal shaping

Model serving

Kubernetes

GPU runtimes

Cost economics

Customer engagement

Tools

vLLM

TensorRT-LLM

Triton

Job description

CoreWeave is seeking a Solution Specialist for AI Runtime Services to bring new runtime offerings to market and drive early adoption. You will own the commercial and technical strategy for net new customer wins, focusing on high-throughput model serving and secure multi-tenant execution.

You will shape roadmaps with product and engineering, engage enterprise buyers, and craft deal structures that accelerate adoption of Inference and Sandboxes, leveraging performance tradeoffs and cost-per-token